Hugging Face's logo

JayBDev
/
my_finetuned_wnut_model_1012

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
my_finetuned_wnut_model_1012 / README.md
JayBDev's picture
JayBDev
End of training
1a4dd37 verified
preview code
|
raw history blame contribute delete
No virus
1.63 kB
metadata
license: mit
base_model: dslim/bert-base-NER
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: my_finetuned_wnut_model_1012
    results: []

my_finetuned_wnut_model_1012

This model is a fine-tuned version of dslim/bert-base-NER on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2611
  • Precision: 0.5882
  • Recall: 0.3865
  • F1: 0.4664
  • Accuracy: 0.9487

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 213 0.2453 0.5159 0.3753 0.4345 0.9464
No log 2.0 426 0.2611 0.5882 0.3865 0.4664 0.9487

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1
  • Datasets 2.18.0
  • Tokenizers 0.15.2